zhayujie
c5b8e06891
feat(channel): add Discord channel
2026-05-30 18:20:27 +08:00
zhayujie
b0ac0731c7
Merge branch 'master' into feat/wechatcom-kf-channel
2026-05-30 17:17:29 +08:00
zhayujie
aa3f48e93c
fix(web): confine /api/file to allowed dirs to prevent arbitrary file read
2026-05-30 17:06:58 +08:00
zhayujie
5ae1e1adde
feat(channel): support slack bot
2026-05-30 17:01:42 +08:00
zhayujie
3dd4b84179
feat(models): support claude-opus-4-8
2026-05-29 10:19:45 +08:00
zhayujie
e3eacc77d7
feat(channel): support telegram bot
2026-05-28 15:07:09 +08:00
6vision
6e04ea8240
refactor(wechat_kf): rename channel from wechatcom_kf and split corp_id
...
Rename the WeCom customer-service channel and give it its own corp_id
field so users no longer have to share `wechatcom_corp_id` with the
self-built WeCom app channel.
Renames (channel-side):
- channel type / const: wechatcom_kf -> wechat_kf
- package dir: channel/wechatcom_kf/ -> channel/wechat_kf/
- python files / classes: WechatComKf* -> WechatKf*
- config keys: wechatcom_kf_{secret,token,aes_key,port} ->
wechat_kf_{secret,token,aes_key,port}; new wechat_kf_corp_id
- env vars: WECHATCOM_KF_* -> WECHAT_KF_*; new WECHAT_KF_CORP_ID
- log prefix / cursor file: [wechatcom_kf] -> [wechat_kf]
- web console CHANNEL_DEFS key + startup log line
Renames (docs):
- docs/channels/wecom-kf.mdx -> docs/channels/wechat-kf.mdx (zh/en/ja)
- update docs.json sidebar entries and all field names inside the docs
In addition, the Web Console "微信客服" entry now exposes its own
Corp ID field instead of reusing the wechatcom_app one, and includes
the screenshot of the visual config in the channel guide.
Web Console onboarding section is added (Tabs: Web Console / config
file) and the local URL `http://127.0.0.1:9899/ ` parenthetical is
dropped for consistency with other channel docs.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-05-28 12:12:44 +08:00
zhayujie
d106465419
feat(channel): telegram first version
2026-05-28 12:10:00 +08:00
zhayujie
bccce2d7cb
feat(models): support xiaomi mimo
2026-05-28 10:49:52 +08:00
6vision
6721dbdbcc
docs(wechatcom_kf): add web console onboarding tab
2026-05-27 21:53:54 +08:00
zhayujie
8d67177a1b
feat(agent): support user-initiated cancel for in-flight agent runs
2026-05-26 23:36:09 +08:00
zhayujie
e05f85f3ce
feat: optimize model name display in English
2026-05-25 15:09:53 +08:00
zhayujie
eb74b73351
fix(web): handle non-string web_password to avoid login TypeError
2026-05-25 11:14:14 +08:00
zhayujie
bd85fee7d7
fix(models): persist explicit provider for vision and image capabilities
2026-05-23 20:43:25 +08:00
zhayujie
cc10d230b0
Merge pull request #2826 from zhayujie/feat-multi-model
...
feat: multi-provider model console
2026-05-22 11:08:13 +08:00
zhayujie
2517f2add8
feat(models): support gpt-5.5
2026-05-22 11:04:55 +08:00
zhayujie
a534266025
feat(models): add qwen3.7-max
2026-05-22 10:54:56 +08:00
zhayujie
8c25395805
feat(models): support gemini-3.5-flash
2026-05-22 10:39:04 +08:00
zhayujie
36b913124b
docs: update models and channels doc
2026-05-22 10:10:07 +08:00
zhayujie
90773ab69f
feat(models): allow viewing and editing search vendor credentials
2026-05-21 20:22:09 +08:00
zhayujie
b7734c3926
feat(search): multi-provider web search + console integration
...
Search tool now supports 4 backends with unified output (bocha,
qianfan, zhipu, linkai) and a routing layer:
- strategy 'auto' (default): pick first configured in canonical order
bocha > qianfan > zhipu > linkai
- strategy 'fixed': pin a specific provider
- agent may pass `provider` to override per-call (only exposed when
≥2 providers configured + auto strategy)
2026-05-21 19:58:03 +08:00
zhayujie
b8333e351c
feat(voice): rework TTS/ASR stack and unify tool/skill config schema
2026-05-21 16:00:54 +08:00
zhayujie
7c35df7a82
fix: default agent mode to enabled
2026-05-21 11:14:19 +08:00
zhayujie
2b90f377e6
feat(voice): add dashscope & zhipu ASR, in-page mic input
2026-05-20 22:36:37 +08:00
zhayujie
fff7326209
feat(memory): hot-swap embedding provider on rebuild-index
...
Switching embedding provider in the web console no longer requires a
restart and no longer drops the running conversation
2026-05-20 21:32:53 +08:00
zhayujie
c181e500bc
feat(web): redesign multi-models console
...
Overhauls the Models tab in the Web Console with a vendor-first layout and
ships a runtime-accurate dispatcher view for vision and image generation.
2026-05-20 20:59:04 +08:00
zhayujie
4634a7bc2f
fix(web): avoid TypeError on single-file upload
2026-05-17 19:00:07 +08:00
zhayujie
16d9b449c9
feat(web): set the web_host to the default value of 127.0.0.1
2026-05-16 18:18:17 +08:00
zhayujie
8761997757
feat(web): add web_host config and password hint for safer deployment
2026-05-16 17:37:07 +08:00
tianyu Gu
a0b29d1ffe
fix(web): remove upload dir button, one-time upload all files,path check adapt windows
2026-05-15 18:48:37 +08:00
tianyu Gu
246f0a45c8
feat(web): support folder upload
2026-05-14 17:16:11 +08:00
zhayujie
20d8ae19a7
Merge pull request #2804 from yangluxin613/feat/web-port-browser
...
feat(web): auto-switch port on conflict and open browser on startup
2026-05-12 10:35:49 +08:00
ooaaooaa123
ad51aabfd7
feat(web): open browser on startup with safe fallback; friendly error on port conflict
2026-05-10 19:30:07 +08:00
zhayujie
907825601d
feat(models): add baidu ernie-5.1
2026-05-10 18:39:38 +08:00
ooaaooaa123
d2d5d98d78
feat(web): auto-switch port on conflict and open browser on startup
2026-05-10 17:20:45 +08:00
zhayujie
a5790d82f6
feat(qianfan): scope vision support to multimodal models
2026-05-06 16:11:10 +08:00
zhayujie
c322c0e3a5
docs(models): add ernie-5.0
2026-05-06 12:15:14 +08:00
zhayujie
530fc20596
Merge pull request #2790 from jimmyzhuu/feat/qianfan-provider
...
Add first-class Baidu Qianfan / ERNIE provider
2026-05-06 11:43:32 +08:00
zhayujie
a9c8a59f58
feat(feishu): one-click QR-scan app creation
2026-05-05 18:32:58 +08:00
jimmyzhuu
f653483eea
feat: expose qianfan in configuration surfaces
2026-04-29 16:32:53 +08:00
zhayujie
5c65196e44
feat(web): hint API base version path in config placeholder
2026-04-26 17:10:24 +08:00
zhayujie
0e556b3468
feat: switch default model to deepseek-v4-flash
2026-04-26 15:54:50 +08:00
zhayujie
472a8605c0
feat(models): support deepseek-v4-pro and deepseek-v4-flash
2026-04-24 11:35:38 +08:00
zhayujie
b0e00dfceb
feat: support glm-5.1
2026-04-23 16:43:05 +08:00
zhayujie
81e8bb62ae
feat(skill): support gpt-image-2 in image generation skill
2026-04-22 20:39:49 +08:00
zhayujie
2c13e1b923
feat(models): support kimi-k2.6
2026-04-22 12:01:40 +08:00
zhayujie
a0748c2e3b
fix(web): cap reasoning content to 4KB across stream/storage/display
2026-04-21 20:31:38 +08:00
zhayujie
6dd316547f
fix(web): fix session title generation fallback and reset Bridge on config change
2026-04-19 18:43:48 +08:00
zhayujie
c82515a927
fix(agent): don't drop tool_calls from empty-response retry
2026-04-18 20:50:40 +08:00
zhayujie
13370d2056
fix: thinking display is disabled by default
2026-04-17 15:31:59 +08:00
